Smadja 2013.

Study characteristics
Patient Sampling	Retrospective, single centre, case‐control study. Normal eyes were selected from suitable candidates undergoing a screening examination for refractive surgery and among the general population undergoing a routine ophthalmologic examination.
Patient characteristics and setting	Normal eyes: discontinued daily‐wear soft contact lens use at least 1 week before evaluation. Eyes were considered normal when no clinical signs of keratoconus and no suggestive topographic or tomographic patterns of suspect keratoconus were found, such as asymmetric bowtie with a skewed radial axes, focal or inferior steepening, central keratometry > 47.0 D, or corneas thinner than 500 mm. Exclusion criteria: previous ocular surgery, ocular pathology, familial history of keratoconus, and contact lens wearing in the past week. Forme‐fruste keratoconus: evident keratoconus in the fellow eye. These eyes had no clinical signs of keratoconus and a normal topographic aspect with no asymmetric bowtie and no focal or inferior steepening pattern. Keratoconus: corneal topography with asymmetric bowtie pattern or localized steepening, irregular cornea determined by distortion of the retinoscopic or ophthalmoscopic red reflex, and ≥ 1 slit‐lamp finding (stromal thinning, Fleischer's ring > 2 mm arc, Vogt's striae, or corneal scarring). Exclusion criteria: specific treatment for keratoconus (e.g. collagen cross‐linking, intracorneal rings, keratoplasty) and marginal pellucid degeneration.
Index tests	A new screening program for the detection of forme fruste keratoconus using the GALILEI Dual Scheimpflug Analyzer (Ziemer Ophthalmic Systems AG, Port, Switzerland). The method is based on an automated decision tree classification that helps to discriminate between normal corneas, forme fruste keratoconus eyes, and keratoconus eyes.
Target condition and reference standard(s)	Participants were divided into 3 groups, but it was unclear who made the diagnosis. The diagnoses were made before the analysis with the classification tree.
Flow and timing	It was unclear if the diagnoses were made by the same person(s). All participants were included in the analyses.
Comparative	Different algorithms were developed. It was unclear whether the results were interpreted separately. All data were included in the different analyses.
Notes	No funding source mentioned.
Methodological quality
Item	Authors' judgement	Risk of bias	Applicability concerns
DOMAIN 1: Patient selection
Was a consecutive or random sample of patients enrolled?	No
Was a case‐control design avoided?	No
Did the study avoid inappropriate exclusions?	Yes
Could the selection of patients have introduced bias?		High risk
Are there concerns that the included patients and setting do not match the review question?			High
DOMAIN 2: Index test (All tests)
Were the index test results interpreted without knowledge of the results of the reference standard?	Yes
If a threshold was used, was it pre‐specified?	Yes
Was the model designed in an appropriate manner?	Yes
Could the conduct or interpretation of the index test have introduced bias?		Low risk
Are there concerns that the index test, its conduct, or interpretation differ from the review question?			Low concern
DOMAIN 3: Reference standard
Is the reference standard likely to correctly classify the target condition?	Unclear
Were the reference standard results interpreted without knowledge of the results of the index tests?	Yes
Could the reference standard, its conduct, or its interpretation have introduced bias?		Unclear risk
Are there concerns that the target condition as defined by the reference standard does not match the question?			Low concern
DOMAIN 4: Flow and timing
Did all patients receive the same reference standard?	Unclear
Were all patients included in the analysis?	Yes
Could the patient flow have introduced bias?		Unclear risk
DOMAIN 5: Comparative
Were different AI tests were developed and interpreted without knowledge of each other.	Unclear
Are the proportions and reasons for missing data similar for all index tests?	Yes
		Unclear risk